Unsupervised 3D Keypoint Discovery with Multi-View Geometry

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Honari, Sina, Zhao, Chen, Salzmann, Mathieu, Fua, Pascal
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909098000252928
author Honari, Sina
Zhao, Chen
Salzmann, Mathieu
Fua, Pascal
author_facet Honari, Sina
Zhao, Chen
Salzmann, Mathieu
Fua, Pascal
contents Analyzing and training 3D body posture models depend heavily on the availability of joint labels that are commonly acquired through laborious manual annotation of body joints or via marker-based joint localization using carefully curated markers and capturing systems. However, such annotations are not always available, especially for people performing unusual activities. In this paper, we propose an algorithm that learns to discover 3D keypoints on human bodies from multiple-view images without any supervision or labels other than the constraints multiple-view geometry provides. To ensure that the discovered 3D keypoints are meaningful, they are re-projected to each view to estimate the person's mask that the model itself has initially estimated without supervision. Our approach discovers more interpretable and accurate 3D keypoints compared to other state-of-the-art unsupervised approaches on Human3.6M and MPI-INF-3DHP benchmark datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2211_12829
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Unsupervised 3D Keypoint Discovery with Multi-View Geometry
Honari, Sina
Zhao, Chen
Salzmann, Mathieu
Fua, Pascal
Computer Vision and Pattern Recognition
Machine Learning
Analyzing and training 3D body posture models depend heavily on the availability of joint labels that are commonly acquired through laborious manual annotation of body joints or via marker-based joint localization using carefully curated markers and capturing systems. However, such annotations are not always available, especially for people performing unusual activities. In this paper, we propose an algorithm that learns to discover 3D keypoints on human bodies from multiple-view images without any supervision or labels other than the constraints multiple-view geometry provides. To ensure that the discovered 3D keypoints are meaningful, they are re-projected to each view to estimate the person's mask that the model itself has initially estimated without supervision. Our approach discovers more interpretable and accurate 3D keypoints compared to other state-of-the-art unsupervised approaches on Human3.6M and MPI-INF-3DHP benchmark datasets.
title Unsupervised 3D Keypoint Discovery with Multi-View Geometry
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2211.12829